{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3Q73WLMGPXL46VLOT7HVYYAUVL","short_pith_number":"pith:3Q73WLMG","schema_version":"1.0","canonical_sha256":"dc3fbb2d867dd7cf556e9fcf5c6014aac9215ac5ccc87996c2f6c712b79fec5d","source":{"kind":"arxiv","id":"2207.02750","version":1},"attestation_state":"computed","paper":{"title":"An SDE perspective on stochastic convex optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Hedy Attouch, Jalal Fadili, Rodrigo Maulen-Soto","submitted_at":"2022-07-06T15:38:32Z","abstract_excerpt":"We analyze the global and local behavior of gradient-like flows under stochastic errors towards the aim of solving convex optimization problems with noisy gradient input. We first study the unconstrained differentiable convex case, using a stochastic differential equation where the drift term is minus the gradient of the objective function and the diffusion term is either bounded or square-integrable. In this context, under Lipschitz continuity of the gradient, our first main result shows almost sure convergence of the objective and the trajectory process towards a minimizer of the objective f"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2207.02750","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-07-06T15:38:32Z","cross_cats_sorted":[],"title_canon_sha256":"3ec696df4f3919900ef781097448645c6d5f0a5474776dc696e75bdc809fe712","abstract_canon_sha256":"1b9cb62838ea781a00373c0aae6cc8030fa89481c32866d47fb30127fce2ced5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:29.010012Z","signature_b64":"zxriHcQU52+LOx1VK/tCLsrptwmGlzDdPvi/VWrMxDJn1464u3A+oYaF1HI0ibHaz5PQXjjmuxdpaGOURQpODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc3fbb2d867dd7cf556e9fcf5c6014aac9215ac5ccc87996c2f6c712b79fec5d","last_reissued_at":"2026-07-05T07:54:29.009670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:29.009670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An SDE perspective on stochastic convex optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Hedy Attouch, Jalal Fadili, Rodrigo Maulen-Soto","submitted_at":"2022-07-06T15:38:32Z","abstract_excerpt":"We analyze the global and local behavior of gradient-like flows under stochastic errors towards the aim of solving convex optimization problems with noisy gradient input. We first study the unconstrained differentiable convex case, using a stochastic differential equation where the drift term is minus the gradient of the objective function and the diffusion term is either bounded or square-integrable. In this context, under Lipschitz continuity of the gradient, our first main result shows almost sure convergence of the objective and the trajectory process towards a minimizer of the objective f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.02750","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2207.02750/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2207.02750","created_at":"2026-07-05T07:54:29.009723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.02750v1","created_at":"2026-07-05T07:54:29.009723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.02750","created_at":"2026-07-05T07:54:29.009723+00:00"},{"alias_kind":"pith_short_12","alias_value":"3Q73WLMGPXL4","created_at":"2026-07-05T07:54:29.009723+00:00"},{"alias_kind":"pith_short_16","alias_value":"3Q73WLMGPXL46VLO","created_at":"2026-07-05T07:54:29.009723+00:00"},{"alias_kind":"pith_short_8","alias_value":"3Q73WLMG","created_at":"2026-07-05T07:54:29.009723+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.04777","citing_title":"Optimization Hyper-parameter Laws for Large Language Models","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3Q73WLMGPXL46VLOT7HVYYAUVL","json":"https://pith.science/pith/3Q73WLMGPXL46VLOT7HVYYAUVL.json","graph_json":"https://pith.science/api/pith-number/3Q73WLMGPXL46VLOT7HVYYAUVL/graph.json","events_json":"https://pith.science/api/pith-number/3Q73WLMGPXL46VLOT7HVYYAUVL/events.json","paper":"https://pith.science/paper/3Q73WLMG"},"agent_actions":{"view_html":"https://pith.science/pith/3Q73WLMGPXL46VLOT7HVYYAUVL","download_json":"https://pith.science/pith/3Q73WLMGPXL46VLOT7HVYYAUVL.json","view_paper":"https://pith.science/paper/3Q73WLMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.02750&json=true","fetch_graph":"https://pith.science/api/pith-number/3Q73WLMGPXL46VLOT7HVYYAUVL/graph.json","fetch_events":"https://pith.science/api/pith-number/3Q73WLMGPXL46VLOT7HVYYAUVL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3Q73WLMGPXL46VLOT7HVYYAUVL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3Q73WLMGPXL46VLOT7HVYYAUVL/action/storage_attestation","attest_author":"https://pith.science/pith/3Q73WLMGPXL46VLOT7HVYYAUVL/action/author_attestation","sign_citation":"https://pith.science/pith/3Q73WLMGPXL46VLOT7HVYYAUVL/action/citation_signature","submit_replication":"https://pith.science/pith/3Q73WLMGPXL46VLOT7HVYYAUVL/action/replication_record"}},"created_at":"2026-07-05T07:54:29.009723+00:00","updated_at":"2026-07-05T07:54:29.009723+00:00"}